华南理工大学学报（自然科学版）2026，Vol.54Issue(5)：28-36,9.DOI:10.12141/j.issn.1000-565X.250284
参考图像引导与风格增强的古壁画图像修复方法
A Reference Image-Guided and Style-Enhanced Restoration Method for Ancient Mural Images
摘要
Abstract
To address the issues of semantic inconsistency and detail blurring in the restoration of ancient mural images using existing deep learning methods,which often solely rely on their own internal prior information and lack external feature guidance,this paper proposes a reference image-guided and style-enhanced restoration method for ancient mural images.First,a backbone network for mural image restoration was constructed,along with a mural feature encoding module based on adaptive cross-scale convolution,which extracts mural content features across scales,thereby enhancing the model's ability to restore fine details.Second,a style feature encoding module was designed to learn and extract multi-scale style features from reference mural images.Third,a feature alignment and fusion module was introduced to align and fuse the mural content features extracted by the encoder of the mural image restoration network with the style features of the reference mural image,serving as external style feature gui-dance.Fourth,a style perception enhancement module was constructed to further refine the fused style features.Meanwhile,a dynamic feature guidance layer was designed within the decoding part of the restoration network to guide the restoration process,improving the semantic consistency of the final restored mural image.Finally,restora-tion experiments were conducted on the Dunhuang mural dataset.Quantitative analysis was performed using Peak Signal-to-Noise Ratio(PSNR)and Structural Similarity Index Measure(SSIM)as objective evaluation metrics.The results indicate that the proposed method can effectively restore the damaged mural images,achieving superior per-formance in both objective and subjective evaluations compared with competing methods.关键词
壁画图像修复/参考图像引导/风格增强/特征对齐融合/引导修复Key words
mural image restoration/reference image guidance/style enhancement/feature alignment and fu-sion/guided restoration分类
信息技术与安全科学引用本文复制引用
陈永,张世龙,范志欣..参考图像引导与风格增强的古壁画图像修复方法[J].华南理工大学学报（自然科学版）,2026,54(5):28-36,9.基金项目
国家自然科学基金项目(62462043,61963023) （62462043,61963023）
甘肃省创新之星项目(2025CXZX-680)Supported by the National Natural Science Foundation of China(62462043,61963023)and the Innovation Star Project Fund of Gansu Province(2025CXZX-680) （2025CXZX-680）
